Back to skill

Security audit

Ozon-关键词趋势 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill does the advertised Ozon keyword-trend lookup, but it also tells the agent to install and configure external software on the host automatically if dependencies are missing.

Install only if you trust Qinghu qhkit and are comfortable with the agent installing Node/npm tooling, changing qhkit configuration, and using an API token. Prefer reviewing or running setup commands yourself, protect the token, and confirm paid Qinghu credit use before calls.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says the skill must trigger when the user says specific phrases "或提出同类需求时必须触发", but it does not define what counts as a similar request. That creates a broad, ambiguous activation boundary and could cause unintended invocation for loosely related Ozon or keyword-analysis requests.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Although the skill is described as a keyword-trend lookup, it also contains extensive environment bootstrapping steps that install Node, install global npm packages, and fetch binaries from the network. This expands the skill from data retrieval into system modification, increasing attack surface and exposing users to package, binary, and configuration risks unrelated to the core task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill includes shell commands for installing software and handling API tokens, but does not present an upfront warning that these actions modify the host, access external networks, and may expose secrets if entered in shared shells or logs. In a hostile or poorly controlled environment, this can lead to unintended system changes and credential leakage.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which makes execution depend on whatever package version is current at runtime. That creates a supply-chain risk: a future compromised or breaking release could be fetched and executed automatically in the user environment.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This duplicated finding points to the same persistence behavior: unpacking software into a user-controlled directory and instructing PATH changes that may outlive the session. Such persistence increases risk because later shells may implicitly trust and execute the installed binaries without the user revisiting the original decision.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This duplicated finding points to the same persistence behavior: unpacking software into a user-controlled directory and instructing PATH changes that may outlive the session. Such persistence increases risk because later shells may implicitly trust and execute the installed binaries without the user revisiting the original decision.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Static analysis

No suspicious patterns detected.